Tricks and Plug-ins for Gradient Boosting in Image Classification
This work addresses efficiency and performance issues in CNN-based image classification, though it appears incremental as it builds on existing boosting methods.
The paper tackles the computational expense and manual tuning required for CNNs in image classification by introducing a framework that integrates dynamic feature selection with BoostCNN principles, using subgrid selection and importance sampling. Experimental results show that their boosted CNN variants outperform conventional CNNs in both accuracy and training speed across fine-grained classification benchmarks.
Convolutional Neural Networks (CNNs) have achieved remarkable success across a wide range of machine learning tasks by leveraging hierarchical feature learning through deep architectures. However, the large number of layers and millions of parameters often make CNNs computationally expensive to train, requiring extensive time and manual tuning to discover optimal architectures. In this paper, we introduce a novel framework for boosting CNN performance that integrates dynamic feature selection with the principles of BoostCNN. Our approach incorporates two key strategies: subgrid selection and importance sampling, to guide training toward informative regions of the feature space. We further develop a family of algorithms that embed boosting weights directly into the network training process using a least squares loss formulation. This integration not only alleviates the burden of manual architecture design but also enhances accuracy and efficiency. Experimental results across several fine-grained classification benchmarks demonstrate that our boosted CNN variants consistently outperform conventional CNNs in both predictive performance and training speed.